检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Chang, Dongliang Pang, Kaiyue Zheng, Yixiao Ma, Zhanyu Song, Yi-Zhe Guo, Jun The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China SketchX CVSSP University of Surrey London United Kingdom

Whether what you see in Figure 1 is a "flamingo" or a "bird", is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former, for the majority of us non-experts just "bird" would probably suffice. The real question is therefore – how can we tailor for different fine-grained definitions under divergent levels of expertise. For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy – so that our answer becomes "bird" = "Phoenicopteriformes" = "Phoenicopteridae" = "flamingo". To approach this new problem, we first conduct a comprehensive human study where we confirm that most participants prefer multi-granularity labels, regardless whether they consider themselves experts. We then discover the key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier. This discovery enables us to design a very simple albeit surprisingly effective solution to our new problem, where we (i) leverage level-specific classification heads to disentangle coarse-level features with fine-grained ones, and (ii) allow finer-grained features to participate in coarser-grained label predictions, which in turn helps with better disentanglement. Experiments show that our method achieves superior performance in the new FGVC setting, and performs better than state-of-the-art on the traditional single-label FGVC problem as well. Thanks to its simplicity, our method can be easily implemented on top of any existing FGVC frameworks and is parameter-free. © 2020, CC BY.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Consensus-Based Distributed Algorithm for Gep

SSRN

引用

SSRN 2022年

作者： Lv, Kexin He, Fan Huang, Xiaolin Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai200240 China

Generalized eigenvalue problem (GEP) plays a significant role in signal processing and machine learning. This paper proposes a consensus-based distributed algorithm for GEP in multi-agent systems, where data samples are distributively stored across agents. The distributed GEP is reformulated as a consensus optimization, but the presence of its quadratic inseparable constraint makes the considered problem more challenging. To deal with it, a sequential method is proposed combined with the alternating direction method of multipliers, which requires communication between couples of nodes. Theoretical analysis shows the proposed algorithm will converge to the set of stationary solutions. And the numerical experiments on synthetic and real-world datasets validate that the approximated solution is competitive to the ground truth. © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Research on the identification of obstacle image based on convolutional neural network

Research on the identification of obstacle image based on co...

引用

2021 International Conference on Signal Image Processing and Communication, ICSIPC 2021

作者： Zhongyu, Li Huajun, Wang Yuhang, Cao Yuting, Dai College of Geophysics Chengdu University of Technology Chengdu610059 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China College of Computer Science Chengdu Normal University Chengdu611130 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China Key Laboratory of Interior Layout Optimization and Security Institutions of Higher Education of Sichuan Province Chengdu Normal University Chengdu Sichuan611130 China

ISBN: (数字)9781510645417

ISBN: (纸本)9781510645400

To effectively realize the reasonable obstacle avoidance of the detection robot, VGG based obstacle discrimination method is proposed. Above all, the image captured by the robot is input into the multi-layer convolutional neural network to obtain the high-level image features, which are used to construct the more accurate neural network model parameters and to train the softmax classifier with these parameters. Then the distance between the imported images and the data images is calculated by using the softmax classifier, and the similarity between the obstacles and non-obstacles is estimated. The experimental results show that the discrimination accuracy increase to above 94%. And the proposed method is more effectively compared with traditional ultrasonic and radar methods. © 2021 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution reconstruction based on self-similarity and neural networks

Image super-resolution reconstruction based on self-similari...

引用

2012 11th International Conference on Information Science, Signal Processing and their Applications, ISSPA 2012

作者： Xu, Yan Li, Xue M. Gao, Tian Suen, Ching Y. Beijing Key Laboratory of Network System and Network Culture University of Posts and Telecommunications Beijing 100876 China Centre for Pattern Recognition and Machine Intelligence Concordia University Montreal QC H3G 1M8 Canada School of Computer Shandong Jianzhu University Jinan 250101 China

ISBN: (纸本)9781467303828

A novel super-resolution approach is presented. An image pyramid has been built based on the framework of wavelet transform, and the detailed coefficients are explored for training the neural networks. The initial high resolution image is estimated by the trained networks and the inverse wavelet transform, and then is constrained with prior knowledge of the error function by iteration. For a factor of 2n, repeat this process and update the networks. The experimental results show that our method reconstructs the more reliable image without obvious visual artifacts. © 2012 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

The Application of A Novel Target Region Extraction Model Based on Object-Accumulated Visual Attention Mechanism

The Application of A Novel Target Region Extraction Model Ba...

引用

International Conference on Natural Computation (ICNC)

作者： Jie Xiao Chao Cai Mingyue Ding Chengping Zhou Institute of Pattern Recognition and Artificial Intelligence State Education Commission Key Laboratory for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China

Combining bottom-up and top-down attention influences, a novel region extraction model which based on object-accumulated visual attention mechanism is proposed in this paper. Compared with early research, the new approach brings in prior information at the proper time, updates scan path dynamically, needs less computational resources and reduces the probability to direct the attention to a less-meaning area. The application to search an airport target in remote sensing image was provided, through which the novel mechanism that how visual attention chose the area was described. Compared with another two region extraction models, experimental results confirm the effectiveness of the approach proposed in this paper.

关键词： Data mining Object detection Computer applications Chaos pattern recognition Artificial intelligence Laboratories Image processing intelligent control Airports

来源：评论

学校读者我要写书评

暂无评论

Blind source separation with evolution based KICA

Blind source separation with evolution based KICA

引用

Asia Pacific Conference on Multimedia and Broadcasting (APMediaCast)

作者： Peng Wu Qian Yin Ping Guo Image Processing and Pattern Recognition Laboratory Beijing Normal University Beijing China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan China

ISBN: (纸本)9781479979684

Kernel independent component analysis (KICA) has been widely used in the field of blind source separation. The selection of kernel function and its parameters plays an important role in KICA algorithm performance. An optimal kernel model should be rich enough to well map the given samples. However, users usually use a singular kernel based model in their experiments, which leads to a suboptimal kernel model. In order to solve this problem, we propose the evolution based multiple kernel independent component analysis (EMKICA), in which a convex combination of multiple base kernels is used instead of single kernel of KICA. The combination weights are learned by particle swarm optimization algorithm. Firstly, we elaborate the basic theory of KICA and concept of EMKICA, also the combination form of the composition kernel used in EMKICA. Secondly, we describe the presentation of the individuals in the particle swarm optimization algorithm, the settings of the evaluation function and general algorithm. Finally, we evaluate the separation ability of EMKICA on three different data sets including one-dimensional mixed signals, composite images and images with reflection. The experimental results verify the effectiveness of EMKICA.

关键词： Kernel Independent component analysis Algorithm design and analysis Multimedia communication Correlation Optimization Asia

来源：评论

学校读者我要写书评

暂无评论

Large second-harmonic vortex beam generation with quasi-nonlinear spin–orbit interaction

引用

Science Bulletin 2021年第5期66卷 449-456,M0004页

作者： Wenchao Zhao Kai Wang Xuanmiao Hong Bingxia Wang Xiaobo Han Kun Wang Weiwei Liu Hua Long Bing Wang Peixiang Lu Wuhan National Laboratory for Optoelectronics and School of Physics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of TechnologyWuhan 430205China Guangdong Intelligent Robotics Institute Dongguan 523808China CAS Center for Excellence in Ultra-intense Laser Science Shanghai 201800China

A harmonic vortex beam is a typical vector beam with a helical wavefront at harmonic frequencies(e.g.,second and third harmonics). It provides an additional degree of freedom beyond spin-and orbitalangular momentum, which may greatly increase the capacity for communicating and encoding information. However, conventional harmonic vortex beam generators suffer from complex designs and a low nonlinear conversion efficiency. Here, we propose and experimentally demonstrate the generation of a large second-harmonic(SH) vortex beam with quasi-nonlinear spin–orbit interaction(SOI). Highquality SH vortex beams with large topological charges up to 28 are realized experimentally. This indicated that the quasi-angular-momentum of a plasmonic spiral phase plate at the excitation wavelength(topological charge, q) could be imprinted on the harmonic signals from the attached WS2 monolayer. The generated harmonic vortex beam has a topological charge of l_(n)= 2 nq(n is the harmonic order). The results may open new avenues for generating harmonic optical vortices for optical communications and enables novel multi-functional hybrid metasurface devices to manipulate harmonic beams.

关键词： Plasmonic metasurface Orbital-angular momentum Monolayer WS_(2) Second-harmonic generation Metalenses

来源：评论

学校读者我要写书评

暂无评论

An SVM-based small target segmentation and clustering approach

An SVM-based small target segmentation and clustering approa...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Sheng Zheng Jian Liu Jin-Wen Tian State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780384032

Segmentation and clustering of infrared small target images in a sky or sea-sky background is considered in this paper, which is the preprocessing part of the detection and recognition of the moving small targets in an infrared image sequence. The infrared image intensity surface is well fitted by the least squares support vector machines (LS-SVM), and then the maximum extremum points are detected on the well fitted intensity surface by convolving the image with the second order directional derivative operators deduced from the mapped LS-SVM with mixtures of kernels. With the coarse locations, the possible targets are extracted by the clustering analysis. The computer experiments are carried out for the real and simulated sky and sea-sky infrared images. The experimental results demonstrate the proposed approach is effective.

关键词： Infrared detectors Infrared imaging Image segmentation Sea surface Image recognition Target recognition Image sequences Least squares methods Support vector machines Kernel

来源：评论

学校读者我要写书评

暂无评论

FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding

arXiv

引用

arXiv 2023年

作者： Liu, Yuan Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

The advent of highly accurate protein structure prediction methods has fueled an exponential expansion of the protein structure database. Consequently, there is a rising demand for rapid and precise structural homolog search. Traditional alignment-based methods are dedicated to precise comparisons between pairs, exhibiting high accuracy. However, their sluggish processing speed is no longer adequate for managing the current massive volume of data. In response to this challenge, we propose a novel deep-learning approach FoldExplorer. It harnesses the powerful capabilities of graph attention neural networks and protein large language models for protein structures and sequences data processing to generate embeddings for protein structures. The structural embeddings can be used for fast and accurate protein search. And the embeddings also provide insights into the protein space. FoldExplorer demonstrates a substantial performance improvement of 5% to 8% over the current state-of-the-art algorithm on the benchmark datasets. Meanwhile, FoldExplorer does not compromise on search speed and excels particularly in searching on a large-scale dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

pattern Matching with Wildcard Gaps Based on Cross List

Pattern Matching with Wildcard Gaps Based on Cross List

引用

International Symposium on Computational Intelligence and Design, ISCID

作者： Junyan Zhang Chenhui Yang Information Science and Technology College Chengdu University Chengdu China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu China

pattern matching is a fundamental application text retrieval, string query, biological sequence analysis, etc. Therefore, the effective algorithm performing this kind of matching is in great need. In this paper, the wildcard is defines to match any one character in a sequence. Multiple wildcards form a gap. The length of a flexible gap is arbitrary. We design CLPM algorithm by use of cross list index structure to realize pattern matching with flexible wildcard gaps. The preprocessing algorithm is designed to initialize cross list so as to reduce searching space. In CLPM algorithm, the effective intervals is defined and computed based on the start positions of each sub pattern in each string, which help to obtain matching result set. Moreover, the approximate pattern matching is converted to short extract pattern matching. The contrast experiments are done based on DBLP tile data set. The results show that CLMP algorithm has better performance in the same fields.

关键词： pattern matching Indexes Silicon Algorithm design and analysis Approximation algorithms Presses Educational institutions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：